Vehicle detection method and system suitable for non-stop over-limit detection system

By combining weighing, image capture and lidar technology, an absolute coordinate system is established and vehicle position information is judged, and misjudgment or misjudgment problems under the influence of light in the existing technology are solved, and accurate detection of vehicle violations and Get evidence.

CN118942258APending Publication Date: 2024-11-12VANJEE TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310511752.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-09
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the existing non-stop overlimit detection system, image evidence collection technology is affected by lighting conditions and cannot obtain the precise position information of the vehicle, resulting in misjudgment or misjudgment violations.

Method used

Combining weighing equipment, image capture equipment and lidar, by obtaining the vehicle's weight data, image information and point cloud data, establish an absolute coordinate system, determine the vehicle's posture information, determine whether there is any illegal driving behavior, and mark the weighing data Exception, store relevant data.

Benefits of technology

It realizes accurate judgment of vehicle violations, reduces the possibility of misjudgment or missed judgments, and improves the accuracy of evidence collection for traffic safety violations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942258A_ABST
    Figure CN118942258A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle detection method and system suitable for a non-stop over-limit detection system. The method comprises the following steps: when a vehicle runs into a weighing area in a set detection area, obtaining weight data of the vehicle through weighing equipment arranged in the weighing area; capturing the vehicle through capturing equipment to obtain vehicle image information, and judging whether the vehicle has illegal driving behaviors or not according to the vehicle image information; acquiring point cloud data of the vehicle in real time by using a laser radar, marking that the weighing data of the vehicle is abnormal, and determining pose information of the vehicle according to the point cloud data; when it is judged that the vehicle has the illegal driving behavior according to the vehicle image information, whether the vehicle has the illegal driving behavior or not is judged according to the pose information; and when the vehicle is judged to have the illegal driving behavior according to the pose information, determining the illegal driving of the vehicle so as to solve the problem of misjudgment or missed judgment caused by the fact that the evidence obtaining picture effect is influenced by the illumination condition and the accurate position information of the vehicle is lacked in the related technology.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a vehicle detection method and system suitable for a non-stop overload detection system. Background Art

[0002] Current non-stop overload detection systems, such as non-site enforcement systems on highways, often use the image evidence collection technology described in the GA / T832 standard as the main means of evidence collection for traffic safety violations. However, in actual applications, image evidence collection technology is affected by lighting conditions and cannot obtain accurate vehicle location information, so some violations may be misjudged or missed. No effective solution has been proposed to this problem. Summary of the invention

[0003] The embodiments of the present invention provide a vehicle detection method and system applicable to a non-stop overload detection system, so as to at least solve the problem in the prior art that the effect of evidence photos is affected by lighting conditions and misjudgment or missed judgment is caused by lack of accurate vehicle position information.

[0004] The embodiment of the present invention provides a vehicle violation detection method applicable to a non-stop overload detection system, comprising: when a vehicle travels into a weighing area within a set detection area, obtaining weight data of the vehicle by means of a weighing device arranged in the weighing area; when the vehicle travels to a capture position within the set detection area, triggering the capture device to capture the vehicle to obtain vehicle image information, and judging whether the vehicle has a driving violation according to the vehicle image information; when the vehicle enters the detection area, obtaining point cloud data of the vehicle in real time by means of a laser radar, and determining the position information of the vehicle according to the point cloud data; and, when it is judged that the vehicle has a driving violation according to the vehicle image information, judging whether the vehicle has a driving violation according to the position information; when it is judged that the vehicle has a driving violation according to the position information, determining that the vehicle has indeed driven illegally, marking the weighing data of the vehicle as abnormal, and storing the point cloud data of the vehicle, the vehicle image information, the driving violation judgment result based on the position information corresponding to the point cloud, and the driving violation judgment result based on the vehicle image information.

[0005] In an exemplary embodiment, the non-stop overload detection system includes a weighing device; before obtaining the point cloud data of the vehicle, an absolute coordinate system shared by the laser radar, the road where the detection area is located, and the weighing device is established, and the reference object coordinates are established.

[0006] In an exemplary embodiment, establishing the absolute coordinate system includes:

[0007] A three-dimensional rectangular coordinate system is established as an absolute coordinate system, and the driving direction of the vehicle is parallel to the X-axis of the absolute coordinate system, and the Z-axis is perpendicular to the ground;

[0008] The conversion matrix obtained by calibration is used to convert the original point cloud data acquired by the laser radar into point cloud data in an absolute coordinate system.

[0009] In an exemplary embodiment, the method further comprises:

[0010] After establishing the absolute coordinate system, marking and recording the coordinate range of the reference object in the absolute coordinate system, wherein the reference object includes a lane line; and

[0011] The point cloud information containing the reference object is exported as a background frame.

[0012] In an exemplary embodiment, the process of generating the pose information using the point cloud data includes:

[0013] According to each frame of the point cloud data, the absolute three-dimensional coordinates, timestamp and heading angle of the front / rear / left and right boundaries of the vehicle are determined; and the driving direction and speed of the vehicle in the X direction and the driving direction and speed of the vehicle in the Y direction of the absolute coordinate system are determined according to the vehicle posture information at adjacent acquisition moments of the current frame.

[0014] In an exemplary embodiment, the vehicle image information includes a capture location and a capture time, and the method further includes:

[0015] After acquiring the vehicle image information, the frame of posture information closest to the vehicle image capture moment is determined among all vehicles based on the capture time, and the posture information of the vehicle closest to the image capture position is found based on the capture position, and the point cloud data corresponding to the determined posture information is determined as the vehicle point cloud data matching the current vehicle image.

[0016] In an exemplary embodiment, the position information includes the speed and driving direction of the vehicle, and judging whether the vehicle has illegal driving behavior based on the position information includes:

[0017] If the current speed of the vehicle in the X direction is greater than the current maximum speed threshold of the road, it is determined to be speeding; if the current speed of the vehicle in the X direction is less than the set minimum speed threshold, it is determined to be stopped; if the current driving direction of the vehicle in the X direction is opposite to the driving direction set on the road, it is determined to be wrong-way; if the current speed of the vehicle in the X direction is lower than the minimum speed limit on the highway and greater than the minimum speed threshold, it is determined to be a low-speed violation.

[0018] In an exemplary embodiment, the determining whether the vehicle has illegal driving behavior based on the posture information including the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle and the posture information and the lane line coordinates includes:

[0019] Determine the relative position of the vehicle and the lane line based on the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle and the lane line coordinates;

[0020] If the current vehicle is driving within the emergency lane in a non-emergency situation, it is determined as illegal use of the emergency lane; if the current vehicle is driving on the shoulder of the road, it is determined as an illegal behavior; if it is determined based on the posture information and the lane line coordinates that the current vehicle wheels have run over the lane line position, it is determined as line crossing; if it is determined based on the posture information and the lane line coordinates that the current vehicle is driving across the lane line, it is determined as line riding.

[0021] In an exemplary embodiment, the position information includes a heading angle; and judging whether the vehicle has illegal driving behavior based on the position information includes:

[0022] If the left and right boundaries of the vehicle and the heading angle deviate significantly when the vehicle is traveling at a low speed, and the speed direction changes, it is determined to be an illegal U-turn; if the heading angle of the vehicle first fluctuates when the vehicle is traveling at a low speed, and the fluctuation range exceeds the maximum preset angle, and finally the heading angle returns to the normal driving angle range, it is determined to be that the vehicle is traveling around S.

[0023] In an exemplary embodiment, determining the vehicle outer dimensions according to the position in the posture information, and then judging whether the vehicle has illegal driving behavior, includes:

[0024] The outer dimensions of the vehicle are determined based on the point cloud data, and whether the vehicle exceeds the size limit is determined based on the outer dimensions and the size standard corresponding to the vehicle model.

[0025] In an exemplary embodiment, the method further comprises:

[0026] When it is determined that the vehicle is indeed driving in violation of traffic rules, a corresponding algorithm is used to calculate the vehicle weight based on the weighing data according to the specific type of driving violation behavior.

[0027] In an exemplary embodiment, the method further comprises:

[0028] Using a density clustering algorithm or a deep network model, identifying the point cloud data corresponding to the vehicle from each frame of point cloud data;

[0029] Using the Hungarian matching algorithm, matching the point cloud data corresponding to the identified vehicle with the vehicles within the detection area;

[0030] The Kalman filter algorithm is used to predict the position of the vehicle in the detection area at the next moment, so as to track the vehicle.

[0031] In an exemplary embodiment, the method further comprises:

[0032] Acquire the stored point cloud data, the vehicle image information, and the weighing data of the vehicle from the data processing device, and display the point cloud video, the vehicle image, and the weighing information of the vehicle formed based on the point cloud data when the vehicle passes through the detection area

[0033] Based on the same inventive concept, the present invention also provides another vehicle detection method applicable to a non-stop overload detection system, comprising:

[0034] When the vehicle drives into a weighing area within the set detection area, the weight data of the vehicle is obtained by a weighing device arranged in the weighing area;

[0035] When a vehicle enters a set detection area, the laser radar is used to obtain point cloud data of the vehicle in real time, and the position information of the vehicle is determined based on the point cloud data, and whether the vehicle has violated driving regulations is determined based on the position information;

[0036] When a vehicle drives to a capture position within the detection area, the vehicle is captured by a capture device to obtain vehicle image information, and it is determined whether the vehicle has any illegal driving behavior based on the vehicle image information;

[0037] When it is determined that the vehicle has engaged in a driving violation based on the vehicle image information and when it is determined that the vehicle has engaged in a driving violation based on the position information, it is determined that the vehicle has engaged in a driving violation, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the result of the driving violation determination based on the position information corresponding to the point cloud, and the result of the driving violation determination based on the vehicle image information are stored.

[0038] Based on the same inventive concept, the embodiment of the present invention also provides a vehicle detection system suitable for a non-stop overload detection system, including: a weighing device, an image capture device, a laser radar and a data processing device

[0039] The weighing device is arranged in a weighing area within a set detection area, and is used to obtain the weight data of the vehicle when the vehicle passes through the weighing area;

[0040] The image capture device is used to capture the vehicle when the vehicle travels to the capture position within the set detection area to obtain vehicle image information;

[0041] The laser radar is used to obtain point cloud data of the vehicle in real time using the laser radar when the vehicle enters the detection area;

[0042] The data processing device is communicatively connected with the weighing device, the image capturing device and the laser radar, and is used to receive the vehicle image information and the point cloud data of the vehicle;

[0043] The data processing device is also used to determine whether the vehicle has a driving violation according to the vehicle image information, and when it is determined that the vehicle has a driving violation according to the vehicle image information, determine whether the vehicle has a driving violation according to the position information, and after determining that the vehicle has a driving violation according to the position information, determine that the vehicle has indeed a driving violation, mark the weighing data of the vehicle as abnormal, and store the point cloud data of the vehicle, the vehicle image information, the driving violation determination result based on the position information corresponding to the point cloud, and the driving violation determination result based on the vehicle image information; or, the data processing device is also Determine the posture information of the vehicle according to the point cloud data and judge whether the vehicle has a driving violation according to the posture information, and judge whether the vehicle has a driving violation according to the vehicle image information; and when it is judged that the vehicle has a driving violation according to the vehicle image information and that the vehicle has a driving violation according to the posture information, determine that the vehicle does have a driving violation, mark the weighing data of the vehicle as abnormal, and store the point cloud data of the vehicle, the vehicle image information, the weighing data, the driving violation judgment result based on the posture information corresponding to the point cloud, and the driving violation judgment result based on the vehicle image information.

[0044] In an exemplary embodiment, the data processing device for generating the pose information using the point cloud data is specifically used to:

[0045] According to each frame of the point cloud data, the absolute three-dimensional coordinates, timestamp and heading angle of the front / rear / left and right boundaries of the vehicle are determined; and the driving direction and speed of the vehicle in the X direction, as well as the driving direction and speed of the vehicle in the Y direction, are determined according to the vehicle posture information at adjacent acquisition moments of the current frame.

[0046] In an exemplary embodiment, the system further includes: a reproduction device connected to the data processing device;

[0047] The reproduction device is used to obtain the stored point cloud data of the vehicle, the vehicle image information, and the weighing data from the data processing device, and to display the point cloud video, the vehicle image, and the weighing information of the vehicle when the vehicle passes through the detection area based on the point cloud data.

[0048] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned vehicle violation detection method when running.

[0049] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the vehicle violation detection method through the computer program.

[0050] In summary, in an embodiment of the present invention, when a vehicle travels to a weighing area within a set detection area, the weight data of the vehicle is obtained by a weighing device arranged in the weighing area; when the vehicle travels to a capture position within the set detection area, the capture device is triggered to capture the vehicle to obtain vehicle image information, and judge whether the vehicle has illegal driving behavior based on the vehicle image information; when the vehicle enters the detection area, the point cloud data of the vehicle is obtained in real time by using a laser radar, the weighing data of the vehicle is marked as abnormal, and the posture information of the vehicle is determined based on the point cloud data; and, when it is determined that the vehicle has illegal driving behavior based on the vehicle image information, it is determined whether the vehicle has illegal driving behavior based on the posture information; when it is determined that the vehicle has illegal driving behavior based on the posture information, it is determined that the vehicle has indeed violated the driving rules, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the weighing data, the illegal driving behavior judgment result based on the posture information corresponding to the point cloud, and the illegal driving behavior judgment result based on the vehicle image information are stored. By adopting the above technical solution, accurate vehicle location information and speed information can be obtained, and the judgment of road traffic safety violations can be assisted in turn. The above technical solution solves the problem in the related art that the effect of evidence photos is affected by lighting conditions and the lack of accurate vehicle location information leads to misjudgment or missed judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0052] Figure 1Schematic diagram of a hardware environment of a vehicle detection system applicable to a non-stop overload detection system provided by an embodiment of the present invention;

[0053] Figure 2 It is a schematic diagram of the layout of a vehicle detection system applicable to a non-stop overload detection system provided by an embodiment of the present invention;

[0054] Figure 3 It is a schematic diagram of a vehicle detection method applicable to a non-stop overload detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0056] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0057] According to an embodiment of the present invention, a method embodiment of non-site law enforcement is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In view of the problems existing in the image evidence collection technology, the embodiment of the present invention provides a vehicle detection system applicable to the non-stop overload detection system. In this embodiment, the above-mentioned vehicle detection system includes multiple hardware devices, which can be specifically as follows: Figure 1 and 2As shown, it includes a laser radar 101, an image capture device 102, a weighing device 103 and a data processing device 104. The data processing device 104 is connected to other devices through a network, and the network may include but is not limited to at least one of the following: a wired network, a wireless network. The above-mentioned wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the above-mentioned wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. In addition to being connected through a network, the laser radar 102, the image capture device 102, the weighing device 103 and the data processing device 104 can also be connected through a network cable or a serial port.

[0059] The laser radar 101 is a multi-line laser radar, which is used to obtain point cloud data of the vehicle in real time when the vehicle enters the detection area. Figure 1 and Figure 2 It can be seen that a detection area is set in the vehicle detection system. When a vehicle enters the detection area, the laser radar is triggered to perform detection to obtain the point cloud data of the vehicle. Alternatively, the laser radar 101 continues to work. When a vehicle is detected to enter the detection area, the vehicle's entry time is recorded, and when the vehicle exits the detection area, the vehicle's exit time is recorded, and the point cloud data of the vehicle in the detection area is intercepted from all the acquired point cloud data based on the entry time and exit time. This embodiment does not impose any limitation on how to obtain the point cloud data of the vehicle in the detection area.

[0060] The image capture device 102 may be a forensic capture camera, and the image capture device 102 is used to capture the vehicle when the vehicle travels to the capture position within the set detection area to obtain vehicle image information. Specifically, the vehicle image information includes the head image information, panoramic image information, and tail image information of the above-mentioned vehicle, and the image capture device may include: a vehicle head image capture device, a vehicle panoramic image capture device, and a vehicle tail image capture device, wherein the vehicle head image capture device is used to collect the above-mentioned head image information; the vehicle panoramic image capture device is used to collect the above-mentioned panoramic image information, and the vehicle tail image capture device is used to collect the above-mentioned tail image information.

[0061] Through the above methods, the vehicle's head image information, panoramic image information and tail image information are collected by the vehicle head image capture device 1021, the vehicle panoramic image capture device 1022 and the vehicle tail image capture device 1023 respectively, so as to realize multi-angle image shooting and improve the accuracy of vehicle image information acquisition and traffic safety violation judgment.

[0062] The weighing device 103 is disposed in a weighing area within a set detection area, and is used to obtain weight data of the vehicle when the vehicle passes through the weighing area.

[0063] In addition, the laser radar and the image capture device are placed on a first support column at a first predetermined distance in front of the weighing area, so that the vehicle tracking and positioning information and point cloud data acquired by the multi-line laser radar are more accurate and comprehensive; and the image capture device can have a better capture angle, and the collected panoramic image information is more accurate and comprehensive.

[0064] The data processing device 104 may be a server, which is communicatively connected with the image capturing device and the laser radar, and is used to receive the vehicle image information and the point cloud data of the vehicle.

[0065] The data processing device is also used to determine whether the vehicle has a driving violation based on the vehicle image information, and when it is determined that the vehicle has a driving violation based on the vehicle image information, determine whether the vehicle has a driving violation based on the position information, mark the weighing data of the vehicle as abnormal, and after determining that the vehicle has a driving violation based on the position information, determine that the vehicle has indeed a driving violation, and store the point cloud data of the vehicle, the vehicle image information, the weighing data, the driving violation determination result based on the position information corresponding to the point cloud, and the driving violation determination result based on the vehicle image information.

[0066] Alternatively, the data processing device also determines the posture information of the vehicle based on the point cloud data and judges whether the vehicle has any illegal driving behavior based on the posture information, and judges whether the vehicle has any illegal driving behavior based on the vehicle image information; and when it is judged that the vehicle has any illegal driving behavior based on the vehicle image information, and when it is judged that the vehicle has any illegal driving behavior based on the posture information, it is determined that the vehicle has indeed any illegal driving behavior, marks the weighing data of the vehicle as abnormal, and stores the point cloud data of the vehicle, the vehicle image information, the weighing data, the illegal driving behavior judgment result based on the posture information corresponding to the point cloud, and the illegal driving behavior judgment result based on the vehicle image information.

[0067] It should be noted that the step of judging whether the vehicle has violated driving rules based on the vehicle image information can also be performed in an image capture device in some embodiments; and the step of determining the vehicle's posture information based on the point cloud data and judging whether the vehicle has violated driving rules based on the posture information can also be performed in a laser radar. This application does not make any limitation on this.

[0068] In addition, the weighing device 103 is arranged in the detection area, and a weighing area is formed accordingly, which is used to obtain weight information of vehicles passing over it. Specifically, the weighing device 103 can be an integral weighing sensor, or a strip weighing sensor including a group of multiple strip sensors arranged in an interlaced manner. When the weighing device 103 is a strip weighing sensor, the position information and driving trajectory of the vehicle in the weighing area can also be determined according to the time, i.e., the position, when each strip sensor is triggered.

[0069] In one embodiment, before acquiring the point cloud data of the vehicle, an absolute coordinate system shared by the laser radar, the road where the detection area is located, and the weighing device is established, and the reference object coordinates are established. It can be understood that the laser radar, the road where the detection area is located, and the weighing device are placed in the same coordinate system, and the coordinate / position information obtained by each device can be associated and data fused.

[0070] Among them, establishing the absolute coordinate system includes: setting up a three-dimensional rectangular coordinate system as the absolute coordinate system, making the vehicle's driving direction parallel to the X-axis of the absolute coordinate system, and the Z-axis perpendicular to the ground; then, using the conversion matrix obtained by calibration, so that the original point cloud data obtained by the laser radar can be converted into point cloud data in the absolute coordinate system. Specifically, in this embodiment, a density clustering algorithm or a deep network model can be used to identify the point cloud data corresponding to the vehicle from each frame of point cloud data; then, the Hungarian matching algorithm is used to match the point cloud data corresponding to the identified vehicle with the vehicle in the detection area, and the Kalman filter algorithm is used to predict the next moment position of the vehicle in the detection area to achieve tracking of the vehicle.

[0071] Furthermore, after establishing the absolute coordinate system, the coordinate range of the reference object is marked and recorded in the absolute coordinate system, wherein the reference object includes a lane line; and the point cloud information containing the reference object is exported as a background frame. It can be understood that in this embodiment, the coordinate range of the reference object is marked and recorded, and the point cloud information containing the reference object is exported as a background frame, which is used to facilitate the extraction of the point cloud data corresponding to the vehicle from the point cloud data frame obtained by the laser radar after the vehicle enters the detection area. It can be understood that the reference object can also include a barrier strip, a roundabout, etc.

[0072] In one embodiment, the process of generating the pose information using the point cloud data includes:

[0073] According to each frame of the point cloud data, the absolute three-dimensional coordinates, timestamp and heading angle of the front / rear / left and right boundaries of the vehicle are determined; and the driving direction and speed of the vehicle in the X direction and the driving direction and speed of the vehicle in the Y direction of the absolute coordinate system are determined according to the vehicle posture information at adjacent acquisition moments of the current frame.

[0074] In this embodiment, after obtaining each frame of vehicle point cloud data, the vehicle's outline size, outline position information (i.e., the absolute three-dimensional coordinates of the front / rear / left and right boundaries), millisecond timestamp, heading angle, driving direction, and speed are determined based on the vehicle's point cloud data. This information constitutes the vehicle's posture information, so that it is possible to judge whether the vehicle has any illegal driving behavior based on the posture information.

[0075] It can also be understood that before determining whether the vehicle has illegal driving behavior based on the vehicle image information and further determining whether the vehicle has illegal driving behavior based on the posture information, it is necessary to match the point cloud data with the vehicle image information. Specifically, the vehicle image information includes the capture location and capture time, and the method further includes:

[0076] After acquiring the vehicle image information, the frame of posture information closest to the vehicle image capture moment is determined among all vehicles based on the capture time, and the posture information of the vehicle closest to the image capture position is found based on the capture position, and the point cloud data corresponding to the determined posture information is determined as the vehicle point cloud data matching the current vehicle image.

[0077] Since the above-mentioned posture information includes information such as vehicle outline, driving status, and spatial position, it is possible to determine whether the vehicle is driving illegally in the detection area based on the point cloud data.

[0078] In one embodiment, when the position information includes the speed and driving direction of the vehicle, judging whether the vehicle has illegal driving behavior based on the position information includes:

[0079] If the current speed of the vehicle in the X direction is greater than the current maximum speed threshold of the road, it is determined to be speeding; if the current speed of the vehicle in the X direction is less than the set minimum speed threshold, it is determined to be stopped; if the current driving direction of the vehicle in the X direction is opposite to the driving direction set on the road, it is determined to be wrong-way; if the current speed of the vehicle in the X direction is lower than the minimum speed limit on the highway and greater than the minimum speed threshold, it is determined to be a low-speed violation.

[0080] If the speed variation range of the current vehicle in the X direction of the weighing area is greater than the set speed range threshold, the non-uniform speed vehicle division algorithm is called to calculate the weight, number of axles, model and other information of the current vehicle; if the current vehicle is determined to be parked, the vehicle stop-go algorithm is called to calculate the weight, number of axles, model and other information of the current vehicle.

[0081] In one embodiment, when the posture information includes the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle, judging whether the vehicle has illegal driving behavior based on the posture information and lane line coordinates includes:

[0082] Determine the relative position of the vehicle and the lane line based on the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle and the lane line coordinates;

[0083] If the current vehicle is driving within the emergency lane in a non-emergency situation, it is determined as illegal use of the emergency lane; if the current vehicle is driving on the shoulder of the road, it is determined as an illegal behavior; if it is determined based on the posture information and the lane line coordinates that the current vehicle wheels have run over the lane line position, it is determined as line crossing; if it is determined based on the posture information and the lane line coordinates that the current vehicle is driving across the lane line, it is determined as line riding.

[0084] If the current vehicle is judged to be crossing the line or riding the line in the weighing area, the cross-lane vehicle separation algorithm is called to calculate the weight, number of axles, model and other information of the current vehicle.

[0085] In one embodiment, when the position information includes a heading angle, judging whether the vehicle has illegal driving behavior based on the position information includes:

[0086] If the left and right boundaries of the vehicle and the heading angle deviate significantly when the vehicle is traveling at a low speed, and the speed direction changes, it is determined to be an illegal U-turn; if the heading angle of the vehicle first fluctuates when the vehicle is traveling at a low speed, and the fluctuation range exceeds the maximum preset angle, and finally the heading angle returns to the normal driving angle range, it is determined to be that the vehicle is traveling around S.

[0087] If the vehicle is currently determined to be traveling around S in the weighing area, the around S vehicle division algorithm is called to calculate the weight, number of axles, model and other information of the current vehicle.

[0088] In one embodiment, determining the outer dimensions of the vehicle according to the position in the posture information, and then judging whether the vehicle has illegal driving behavior, includes:

[0089] The outer dimensions of the vehicle are determined based on the point cloud data, and whether the vehicle exceeds the size limit is determined based on the outer dimensions and the size standard corresponding to the vehicle model.

[0090] In one embodiment, the system further includes a reproduction device, which is connected to the data processing device; the reproduction device is used to obtain the stored point cloud data of the vehicle, the vehicle image information, and the weighing data from the data processing device, and display the point cloud video, the vehicle image, and the weighing information of the vehicle when the vehicle passes through the detection area based on the point cloud data.

[0091] In order to explain the application of the vehicle detection system in more detail, Figure 2 The system shown in the figure is described in detail. Figure 3 As shown, the process of the method may include the following steps:

[0092] Step S300, calibrate the laser radar, include the road in the detection area and the weighing equipment in the absolute coordinate system, mark the coordinates of each lane line, and extract the background frame for subsequent visualization.

[0093] The vehicle violation behavior identification method in this embodiment can be applied to the scene where the overload inspection station is not open to traffic, which can be an area on a highway, ordinary highway or other road where passing vehicles need to be inspected.

[0094] In this step, the X-axis direction of the absolute coordinate system is set to the vehicle driving direction in the lane by default, the Z-axis direction is set to be perpendicular to the ground and upward, the Y-axis is perpendicular to both the X and Z directions, and the vertical coordinate reference of the point cloud on the ground is 0. (Other coordinate system settings are also possible)

[0095] Here, the reference object mainly refers to the lane line. Since the vehicle travels along the X axis, it is only necessary to mark the coordinates of the lane line in the Y direction. In addition, the reference objects shown may also include isolation belts, roundabouts, etc.

[0096] Step S301: When a vehicle drives into a weighing area within a set detection area, the weight data of the vehicle is obtained by a weighing device arranged in the weighing area.

[0097] Step S302, when a vehicle is detected driving into the detection area, the laser radar sensor is used to obtain the point cloud in the detection area in real time; and the data processing unit receives the point cloud sent by the laser radar, identifies and tracks the vehicle, and obtains the vehicle's position information in the current frame.

[0098] In this embodiment, after obtaining the point cloud in the detection area, it is necessary to identify the power source corresponding to the vehicle from a frame of point cloud. The identification method of the vehicle target (i.e., the vehicle in the point cloud frame) is a general technology and is not limited here, including but not limited to density clustering algorithms, deep neural network algorithms, etc.

[0099] Vehicle target tracking technology is also a general technology and is not limited here. It can include SORT, DeepSORT, ByteTrack, etc.

[0100] In addition, the acquisition of vehicle posture is a general technology. The vehicle heading angle can be obtained by L-shape-fitting or similar fitting methods, the vehicle outline can be directly calculated from the vehicle boundary, and the vehicle speed in each direction can be estimated by Kalman filter or direct filtering calculation of historical observation data.

[0101] Step S303: When the vehicle travels to the capture position within the set detection area, the vehicle is captured by a capture device to obtain vehicle image information.

[0102] Specifically, the capture of the vehicle can be triggered by the capture device based on the detected vehicle position, or it can be triggered by an IO signal through a serial port or other connection method. The trigger signal can be given by a weighing device or a data processing device. After the capture device captures the vehicle, the captured vehicle image information is sent to the data processing unit.

[0103] It should be noted that there is no limitation on the execution order of step 301 , step 302 and step 303 , and the three steps can be executed in any order.

[0104] Step S304: Matching the point cloud data of the vehicle with the captured image information through the data processing unit.

[0105] There are many matching methods in this step, including common ID matching, recent time and space matching, event queue matching, etc., which are not limited here.

[0106] Step S305, the data processing device determines whether the vehicle has any illegal driving behavior based on the vehicle image information, and when it is determined that the vehicle has any illegal driving behavior based on the vehicle image information, determines whether the vehicle has any illegal driving behavior based on the position information.

[0107] Step S306, when it is determined that the vehicle has violated driving rules based on the position information, the vehicle is determined to have violated driving rules, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the weighing data, the violation driving behavior determination result based on the position information corresponding to the point cloud, and the violation driving behavior determination result based on the vehicle image information are stored.

[0108] Specifically, after the vehicle leaves the detection area, the illegal driving behavior is comprehensively determined by combining the captured image violation detection results and the laser point cloud violation detection results. Combined with the vehicle weight information, etc., a complete vehicle passing record is formed and stored in the database. The historical point cloud posture information and captured photos of the corresponding vehicle are saved as files for archiving. If there is an upload requirement, the above structured / unstructured data is uploaded to the data platform.

[0109] Optionally, the method further comprises:

[0110] The stored point cloud data, the vehicle image information, and the weighing data of the vehicle are obtained from the data processing device, and a point cloud video, the vehicle image, and the weighing information of the vehicle formed based on the point cloud data when the vehicle passes through the detection area are displayed.

[0111] It is understandable that since the point cloud data of the vehicle has been locally stored on a vehicle-by-vehicle basis, it can be used by the traffic control department to re-evaluate traffic safety violations. The specific methods can be:

[0112] Use computer software or browser plug-ins to display evidence information in multiple dimensions for law enforcement personnel to review. The ways to display evidence information include:

[0113] 1) Display the pictures captured by the evidence camera (including necessary evidence information) and weighing data;

[0114] 2) Play a short video of evidence collection (including necessary evidence collection information);

[0115] 3) Play point cloud video of the vehicle passing through, allowing selection and reading of precise coordinates of the vehicle point cloud, and displaying the front / rear position, left and right boundary positions, and vehicle height information of each frame;

[0116] 4) Display complete vehicle passing records, including license plate, speed, vehicle profile information and identified traffic safety violation categories;

[0117] It is worth noting that the third item of the display method, visualization of the historical point cloud position information of the vehicle, or point cloud video, reproducing the driving process of the illegal vehicle, includes the following steps:

[0118] 1) Import the background frame point cloud containing reference objects such as isolation belts, and display the background point cloud in the 3D interactive window;

[0119] 2) Import lane line coordinate information and overlay lane lines in the window;

[0120] 3) Import the first frame of the corresponding vehicle historical posture information and overlay it in the interactive window;

[0121] 4) Clear the point cloud belonging to the vehicle in the current window;

[0122] 5) Repeat steps 3) and 4) until the point cloud video is finished.

[0123] Optionally, since point cloud data can accurately reproduce the passage of vehicles through the detection area, traffic management departments can also use massive point cloud data of illegal vehicles for big data analysis, discover and avoid risks based on the analysis results, and formulate optimization measures. For example, big data technology can be used to batch analyze point cloud data, and statistically analyze the time patterns of illegal overtaking, road congestion and other events, speed distribution range, lane frequency, vehicle type distribution and other characteristics.

[0124] Above Figure 3 In the method flow chart shown, the step of judging whether the vehicle has a driving violation based on the posture information is not performed each time new posture information is acquired. Instead, after judging that the vehicle has a driving violation based on the vehicle image information, the posture information corresponding to the vehicle image information is used to judge again whether the vehicle actually has a driving violation, so as to improve the accuracy of the judgment and reduce the chance of misjudgment.

[0125] It is understandable that the execution step of judging whether the vehicle has violated driving rules based on the position information may not rely on the judgment result based on the vehicle image information. That is, after each frame of vehicle point cloud data, the data processing device determines the vehicle's position information based on the frame of point cloud data, and judges whether the vehicle has violated driving rules based on the position information; and when judging that the vehicle has violated driving rules based on the vehicle image information and judging that the vehicle has violated driving rules based on the position information, it is determined that the vehicle has indeed violated driving rules. The specific operation will not be repeated here.

[0126] According to another aspect of the embodiment of the present application, a determination device for implementing the above-mentioned illegal vehicle identification method is also provided. The device may include:

[0127] The first acquisition unit is used to acquire real-time point cloud data of the laser radar.

[0128] The second acquisition unit is used to acquire the vehicle image information captured by the evidence camera.

[0129] The first processing unit is used to realize the recognition and tracking of vehicle point cloud targets (i.e., vehicles within the detection area), as well as the matching of vehicle point cloud data with the capture results, and to judge the illegal behavior based on the obtained vehicle image information and point cloud data.

[0130] The second processing unit is used to realize the fusion of vehicle results, data storage and uploading.

[0131] It should be noted that the examples and application scenarios implemented by the above-mentioned units and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments. It should be noted that the above-mentioned units as part of the device can be operated in the following manner: Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0132] According to another aspect of the embodiment of the present application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned vehicle violation behavior methods in the embodiment of the present application.

[0133] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0134] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0135] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0136] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned vehicle violation detection method is also provided. The electronic device can be a server, a terminal, or a combination thereof.

[0137] In one embodiment, the electronic device of the vehicle violation detection method includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, wherein:

[0138] Memory for storing computer programs;

[0139] The processor is used to execute the computer program stored in the memory, and implements the following steps:

[0140] Receiving the vehicle image information and the point cloud data of the vehicle;

[0141] determining whether the vehicle has a driving violation according to the vehicle image information, and determining whether the vehicle has a driving violation according to the position information when the vehicle image information determines that the vehicle has a driving violation.

[0142] After determining that the vehicle has a driving violation according to the position information, determining that the vehicle has indeed a driving violation, and storing the point cloud data of the vehicle, the vehicle image information, a driving violation determination result based on the position information corresponding to the point cloud, and a driving violation determination result based on the vehicle image information;

[0143] Alternatively, when the processor is used to execute the computer program stored in the memory, the following steps are implemented:

[0144] The data processing device is used to receive the vehicle image information and the point cloud data of the vehicle,

[0145] Determine the position information of the vehicle according to the point cloud data and judge whether the vehicle has illegal driving behavior according to the position information, and judge whether the vehicle has illegal driving behavior according to the vehicle image information;

[0146] When it is determined that the vehicle has engaged in illegal driving behavior based on the vehicle image information, and when it is determined that the vehicle has engaged in illegal driving behavior based on the positional information, it is determined that the vehicle has indeed engaged in illegal driving behavior, and the point cloud data of the vehicle, the vehicle image information, the illegal driving behavior determination result based on the positional information corresponding to the point cloud, and the illegal driving behavior determination result based on the vehicle image information are stored.

[0147] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the address bus, the data bus, the control bus, etc. are represented by lines of different thicknesses in the corresponding diagrams, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0148] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0149] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0150] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0151] Those skilled in the art can understand that the structure shown above is only for illustration, and the device for implementing the above method for determining the effective point cloud vector can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. The above embodiments do not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components (such as a network interface, a display device, etc.) than those shown in the above embodiments, or have a configuration different from the above embodiments.

[0152] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0153] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0154] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0155] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0156] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0158] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically separately, or at least two units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0159] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A vehicle detection method applicable to a non-stop overload detection system, characterized in that: include: When the vehicle drives into a weighing area within the set detection area, the weight data of the vehicle is obtained by a weighing device arranged in the weighing area; When a vehicle drives to a capture position within a set detection area, the capture device captures the vehicle to obtain vehicle image information, and determines whether the vehicle has any illegal driving behavior based on the vehicle image information; When a vehicle enters the detection area, the laser radar is used to obtain point cloud data of the vehicle in real time, and the position information of the vehicle is determined according to the point cloud data; and, when it is determined according to the vehicle image information that the vehicle has engaged in illegal driving behavior, determining according to the position information whether the vehicle has engaged in illegal driving behavior; When it is determined that the vehicle has violated driving regulations based on the position information, the vehicle is determined to have violated driving regulations, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the weighing data, the violation driving behavior determination result based on the position information corresponding to the point cloud, and the violation driving behavior determination result based on the vehicle image information are stored.

2. The method according to claim 1, characterized in that The non-stop over-limit detection system includes a weighing device; the method also includes: Before acquiring the point cloud data of the vehicle, an absolute coordinate system shared by the laser radar, the road where the detection area is located, and the weighing device is established, and the coordinates of the reference object are determined.

3. The method according to claim 2, characterized in that Establishing the absolute coordinate system includes: A three-dimensional rectangular coordinate system is established as an absolute coordinate system, and the driving direction of the vehicle is parallel to the X-axis of the absolute coordinate system, and the Z-axis is perpendicular to the ground; The conversion matrix obtained by calibration is used to convert the original point cloud data acquired by the laser radar into point cloud data in an absolute coordinate system.

4. The method according to claim 3, characterized in that Also includes: After establishing the absolute coordinate system, marking and recording the coordinate range of the reference object in the absolute coordinate system, wherein the reference object includes a lane line; as well as The point cloud information containing the reference object is exported as a background frame.

5. The method according to claim 3, characterized in that: The process of generating the pose information using the point cloud data includes: According to each frame of the point cloud data, the absolute three-dimensional coordinates, timestamp and heading angle of the front / rear / left and right boundaries of the vehicle are determined; and the driving direction and speed of the vehicle in the X direction and the driving direction and speed of the vehicle in the Y direction of the absolute coordinate system are determined according to the vehicle posture information at adjacent acquisition moments of the current frame.

6. The method according to claim 1, characterized in that The vehicle image information includes a capture location and a capture time, and the method further includes: After acquiring the vehicle image information, the frame of posture information closest to the vehicle image capture moment is determined among all vehicles based on the capture time, and the posture information of the vehicle closest to the image capture position is found based on the capture position, and the point cloud data corresponding to the determined posture information is determined as the vehicle point cloud data matching the current vehicle image.

7. The method according to claim 1, characterized in that The position information includes the speed and driving direction of the vehicle, and judging whether the vehicle has illegal driving behavior based on the position information includes: If the current speed of the vehicle in the X direction is greater than the current maximum speed threshold of the road, it is determined to be speeding; if the current speed of the vehicle in the X direction is less than the set minimum speed threshold, it is determined to be stopped; if the current driving direction of the vehicle in the X direction is opposite to the driving direction set on the road, it is determined to be wrong-way; if the current speed of the vehicle in the X direction is lower than the minimum speed limit on the highway and greater than the minimum speed threshold, it is determined to be a low-speed violation.

8. The method according to claim 1, characterized in that: The step of determining whether the vehicle has illegal driving behavior based on the posture information including the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle and the posture information and the lane line coordinates includes: Determine the relative position of the vehicle and the lane line based on the absolute three-dimensional coordinates of the front / rear / left and right boundaries of the vehicle and the lane line coordinates; If the current vehicle is driving within the emergency lane in a non-emergency situation, it is determined as illegal use of the emergency lane; if the current vehicle is driving on the shoulder of the road, it is determined as an illegal behavior; if it is determined based on the posture information and the lane line coordinates that the current vehicle wheels have run over the lane line position, it is determined as line crossing; if it is determined based on the posture information and the lane line coordinates that the current vehicle is driving across the lane line, it is determined as line riding.

9. The method according to claim 1, characterized in that: The position information includes a heading angle; judging whether the vehicle has illegal driving behavior based on the position information includes: If the left and right boundaries of the vehicle and the heading angle deviate significantly when the vehicle is traveling at a low speed, and the speed direction changes, it is determined to be an illegal U-turn; if the heading angle of the vehicle first fluctuates when the vehicle is traveling at a low speed, and the fluctuation range exceeds the maximum preset angle, and finally the heading angle returns to the normal driving angle range, it is determined to be that the vehicle is traveling around S.

10. The method according to claim 1, characterized in that The determining of the vehicle outer dimensions according to the position in the posture information, and then judging whether the vehicle has illegal driving behavior, includes: The outer dimensions of the vehicle are determined based on the point cloud data, and whether the vehicle exceeds the size limit is determined based on the outer dimensions and the size standard corresponding to the vehicle model.

11. The method according to any one of claims 1 to 10, characterized in that: Also includes: When it is determined that the vehicle is indeed driving in violation of traffic rules, a corresponding algorithm is used to calculate the vehicle weight based on the weighing data according to the specific type of driving violation behavior.

12. The method according to claim 1, characterized in that Also includes: Using a density clustering algorithm or a deep network model, identifying the point cloud data corresponding to the vehicle from each frame of point cloud data; Using the Hungarian matching algorithm, matching the point cloud data corresponding to the identified vehicle with the vehicles within the detection area; The Kalman filter algorithm is used to predict the position of the vehicle in the detection area at the next moment, so as to track the vehicle.

13. The method according to claim 1, characterized in that Also includes: The stored point cloud data, the vehicle image information, and the weighing data of the vehicle are obtained from the data processing device, and a point cloud video, the vehicle image, and the weighing information of the vehicle formed based on the point cloud data when the vehicle passes through the detection area are displayed.

14. A vehicle detection method applicable to a non-stop overload detection system, characterized in that: include: When the vehicle drives into a weighing area within the set detection area, the weight data of the vehicle is obtained by a weighing device arranged in the weighing area; When a vehicle enters a set detection area, the laser radar is used to obtain point cloud data of the vehicle in real time, and the position information of the vehicle is determined based on the point cloud data, and whether the vehicle has violated driving regulations is determined based on the position information; When a vehicle drives to a capture position within the detection area, the vehicle is captured by a capture device to obtain vehicle image information, and it is determined whether the vehicle has any illegal driving behavior based on the vehicle image information; When it is determined that the vehicle has engaged in a driving violation based on the vehicle image information and when it is determined that the vehicle has engaged in a driving violation based on the position information, it is determined that the vehicle has engaged in a driving violation, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the weighing data, the result of the driving violation determination based on the position information corresponding to the point cloud, and the result of the driving violation determination based on the vehicle image information are stored.

15. A vehicle detection system suitable for a non-stop overload detection system, characterized in that: include: A weighing device is arranged in a weighing area within a set detection area, and is used to obtain weight data of the vehicle when the vehicle passes through the weighing area; An image capture device is used to capture the vehicle when the vehicle travels to a capture position within a set detection area to obtain vehicle image information; A laser radar, used to obtain point cloud data of the vehicle in real time using the laser radar when the vehicle enters the detection area; A data processing device, which is in communication with the weighing device, the image capturing device and the laser radar, and is used to receive the vehicle image information and the point cloud data of the vehicle; The data processing device is also used to determine whether the vehicle has a driving violation based on the vehicle image information, and when it is determined that the vehicle has a driving violation based on the vehicle image information, determine whether the vehicle has a driving violation based on the position information, and after determining that the vehicle has a driving violation based on the position information, determine that the vehicle has indeed a driving violation, mark the weighing data of the vehicle as abnormal, and store the point cloud data of the vehicle, the vehicle image information, the weighing data, the driving violation determination result based on the position information corresponding to the point cloud, and the driving violation determination result based on the vehicle image information; or, The data processing device also determines the position information of the vehicle according to the point cloud data and judges whether the vehicle has illegal driving behavior according to the position information, and judges whether the vehicle has illegal driving behavior according to the vehicle image information; When it is determined that the vehicle has engaged in illegal driving behavior based on the vehicle image information and when it is determined that the vehicle has engaged in illegal driving behavior based on the positional information, it is determined that the vehicle has indeed engaged in illegal driving behavior, the weighing data of the vehicle is marked as abnormal, and the point cloud data of the vehicle, the vehicle image information, the illegal driving behavior determination result based on the positional information corresponding to the point cloud, and the illegal driving behavior determination result based on the vehicle image information are stored.

16. The system according to claim 14, characterized in that The data processing device used to generate the pose information using the point cloud data is specifically used to: According to each frame of the point cloud data, the absolute three-dimensional coordinates, timestamp and heading angle of the front / rear / left and right boundaries of the vehicle are determined; and the driving direction and speed of the vehicle in the X direction, as well as the driving direction and speed of the vehicle in the Y direction, are determined according to the vehicle posture information at adjacent acquisition moments of the current frame.

17. The system according to claim 14, characterized in that Also includes: A reproduction device connected to the data processing device; The reproduction device is used to obtain the stored point cloud data of the vehicle, the vehicle image information, and the weighing data from the data processing device, and to display the point cloud video, the vehicle image, and the weighing information of the vehicle when the vehicle passes through the detection area based on the point cloud data.